A5042431015- Smart Agriculture and AI
- Animal Behavior and Welfare Studies
- Food Supply Chain Traceability
- Marine and coastal plant biology
- Advanced Image and Video Retrieval Techniques
- Robotics and Sensor-Based Localization
- Coastal wetland ecosystem dynamics
- Video Surveillance and Tracking Methods
- Advanced Neural Network Applications
- Marine Biology and Ecology Research
- Effects of Environmental Stressors on Livestock
- Advanced Vision and Imaging
- Remote Sensing in Agriculture
- Leaf Properties and Growth Measurement
- Spectroscopy and Chemometric Analyses
- Coral and Marine Ecosystems Studies
- Plant Disease Management Techniques
- Image Enhancement Techniques
- Remote Sensing and Land Use
- Plant Pathogens and Fungal Diseases
- Image Retrieval and Classification Techniques
- Autonomous Vehicle Technology and Safety
- Soil Mechanics and Vehicle Dynamics
- Human-Animal Interaction Studies
- Industrial Vision Systems and Defect Detection
The University of Adelaide
2023-2025
Australian Centre for Robotic Vision
2019-2024
The University of Sydney
2019-2024
Qingdao University of Science and Technology
2020-2024
Qingdao National Laboratory for Marine Science and Technology
2020-2022
Institute of Oceanology
2020-2022
Chinese Academy of Sciences
2020-2022
Marine Biology Institute of Shandong Province
2021-2022
University of Chinese Academy of Sciences
2022
Université de technologie de belfort-montbéliard
2014-2017
Individual cattle identification is required for precision livestock farming. Current methods individual requires either visual, or unique radio frequency, ear tags. We propose a deep learning based framework to identify beef using image sequences unifying the advantages of both CNN (Convolutional Neural Network) and LSTM (Long Short-Term Memory) network methods. A was used (Inception-V3) extract features from rear-view video dataset these extracted were then train an model capture temporal...
Grape downy mildew (GDM) disease is a common plant leaf disease, and it causes serious damage to grape production, reducing yield fruit quality. Traditional manual detection relies on farm experts often time-consuming. Computer vision technologies artificial intelligence could provide automatic for real-time controlling the spread of grapevine in precision viticulture. To achieve best trade-off between GDM accuracy speed under natural environments, deep learning based approach named...
For commercial broiler production, about 20,000–30,000 birds are raised in each confined house, which has caused growing public concerns on animal welfare. Currently, daily evaluation of wellbeing and growth is conducted manually, labor-intensive subjectively subject to human error.. Therefore, there a need for an automatic tool detect analyze the behaviors chickens predict their welfare status. In this study, we developed YOLOv5-CBAM-broiler model tested its performance detecting broilers...
Seagrass meadows play critical roles in supporting a high level of biodiversity but are continuously threatened by human activities, such as sea reclamation. In this study, we reported on large seagrass (Zostera marina L.) meadow Caofeidian shoal harbor the Bohai Sea northern China. We evaluated environmental impact reclamation activities using Landsat imagery (1974–2019) mapping distribution changes. ISODATA was adopted for unsupervised classification and beds. The error matrix developed...
Cow tail detection and tracking in videos provide valuable information for individual identification, calving process, behavior analysis, body condition monitoring. Although deep learning-based methods have demonstrated good performance, many of them high complexity still require an improvement video object by reducing the computation time false positives. To fully exploit interframe achieve a real-time online detection, optimized cow method is proposed based on improved single shot multibox...
The precision spray of liquid fertilizer and pesticide to plants is an important task for agricultural robots in agriculture. By reducing the amount chemicals being sprayed, it brings a more economic eco-friendly solution compared conventional non-discriminated spray. prerequisite detect track each plant. Conventional detection or segmentation methods all image captured under robotic platform, without knowing ID To pesticides plant exactly once, tracking every needed addition detection. In...
Achieving rapid and accurate detection of apple leaf diseases in the natural environment is essential for growth plants development industry. In recent years, deep learning has been widely studied applied to disease detection. However, existing networks have too many parameters be easily deployed or lack research on complex backgrounds effectively use real agricultural environments. This study proposes a novel network, YOLOX-ASSANano, which an improved lightweight real-time model based...
Maize is susceptible to infect pest disease, and early disease detection key preventing the reduction of maize yields. The raw data used for plant are commonly RGB images hyperspectral (HSI). can be acquired rapidly low-costly, but accuracy not satisfactory. On contrary, using HSIs tends obtain higher accuracy, difficult high-cost in field. To overcome this contradiction, we have proposed spectral recovery framework which includes two parts: network based on advanced convolutional neural...
Individual cattle identification plays an important role for automation in precision livestock management. Existing methods require radio frequency and visual ear tags, all of which are prone to loss or damage. In this work, we propose a deep learning-based framework identify beef using image sequences, unifying merits both Convolutional Neural Network (CNN) Bidirectional Long Short-Term Memory (BiLSTM) network methods. A CNN (Inception-V3) was used extract features from video dataset taken...